Efficiency in Deep Learning: Image and Video Deep Model Efficiency

Research output: ThesisDissertation (TU Delft)

49 Downloads (Pure)

Abstract

Deep learning is the core algorithmic tool for automatically processing large amounts of data. Deep learning models are defined as a stack of functions (called layers) with millions of parameters, that are updated during training by fitting them to data. Deep learning models have show remarkable accuracy gains on visual problems in video and images. Yet at the same time, this comes at a considerable computational cost that raises concerns about energy consumption. The escalation in the number of parameters and the surging demand for extensive data exacerbate these concerns. This thesis delves into the core of these concerns, proposing innovative techniques to enhance the efficiency of deep learning models. This thesis starts with exploring efficient deep learning models for video data, followed by efficient models for image data.....
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • Delft University of Technology
Supervisors/Advisors
  • Reinders, M.J.T., Supervisor
  • van Gemert, J.C., Supervisor
  • Pintea, S., Advisor
Award date16 May 2024
Print ISBNs978-94-6469-947-0
DOIs
Publication statusPublished - 2024

Keywords

  • Efficiency
  • Deep Learning
  • Computer Vision

Fingerprint

Dive into the research topics of 'Efficiency in Deep Learning: Image and Video Deep Model Efficiency'. Together they form a unique fingerprint.

Cite this